Abstract | ||
---|---|---|
In this paper, we propose an algorithm for 12-leads ECG signals feature extraction by Uncorrelated Multilinear Principal Component Analysis(UMPCA). However, traditional algorithms usually base on 2-leads ECG signals and do not efficiently work out for 12-leads signals. Our algorithm aims at the natural 12-leads ECG signals. We firstly do the Short Time Fourier Transformation(STFT) on the raw ECG data and obtain 3rd-order tensors in the spatial-spectral-temporal domain, then take UMPCA to find a Tensor-to-Vector Projection(TVP) for feature extraction. Finally the Support Vector Machine(SVM) classifier is applied to achieve a high accuracy with these features. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1007/978-3-642-39065-4_47 | ISNN (1) |
Keywords | Field | DocType |
traditional algorithm,12-leads signal,support vector machine,feature extraction,raw ecg data,component analysis,12-leads ecg signal,2-leads ecg signal,tensor-to-vector projection,short time fourier transformation,tensor | Tensor,Computer science,Uncorrelated,Short-time Fourier transform,Fourier transform,Artificial intelligence,Classifier (linguistics),Multilinear principal component analysis,Pattern recognition,Support vector machine,Feature extraction,Speech recognition,Machine learning | Conference |
Citations | PageRank | References |
1 | 0.35 | 3 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dong Li | 1 | 475 | 67.20 |
Kai Huang | 2 | 16 | 2.31 |
Hanlin Zhang | 3 | 1 | 0.35 |
Liqing Zhang | 4 | 2713 | 181.40 |